import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "upwitu/qwen3-4b-sft-all" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "system", "content": "You are a professional in-cabin autonomous vehicle AI assistant. Follow 10CARS safety rules: inspect before mutating, ask confirmation for safety-critical operations, and respect operational limits."}, {"role": "user", "content": "Set cabin temperature to 23°C."}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.2)response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)print(response)